Computer-aided method for image feature analysis and diagnosis in mammography
A method for automated detection of abnormal anatomic regions, wherein a mammogram is digitized to produce a digital image and the digital image is processed using local edge gradient analysis and linear pattern analysis in addition to feature extraction routines to identify abnormal anatomic regions. Noise reduction filtering and pit-filling/spike-removal filtering techniques are also provided. Multiple difference imaging techniques are also used in which difference images employing different filter characteristics are obtained and processing results logically OR'ed to identify abnormal anatomic regions. In another embodiment the processing results with and without noise reduction filtering are logically AND'ed to improve detection sensitivity. Also, in another embodiment the wavelet transform is utilized in the identification and detection of abnormal regions. The wavelet transform is preferably used in conjunction with the difference imaging technique with the results of the two techniques being logically OR'ed.
Latest Arch Development Corporation Patents:
- Treatment of tumors with genetically engineered herpes virus
- DNA DAMAGING AGENTS IN COMBINATION WITH TYROSINE KINASE INHIBITORS
- TREATMENT OF TUMORS WITH GENETICALLY ENGINEERED HERPES VIRUS
- Treatment of tumors with genetically engineered herpes virus
- Methods for Identifying Factors That Control the Folding of Amyloid Proteins of Diverse Origin
Claims
1. A method for automated detection of an abnormal anatomic region, comprising:
- obtaining a digital image of an object including said anatomic region;
- subjecting said digital image to noise reduction filtering, comprising,
- subjecting said digital image to wavelet transformation including decomposing said digital image to the wavelet domain and reconstructing said digital image based on second and third level components in the decomposed digital image; and
- performing predetermined signal extraction and feature analysis routines on the reconstructed digital image to identify locations of candidate abnormal regions.
2. The method of claim 1, further comprising:
- processing the candidate abnormal regions to identify abnormal regions from among said candidate abnormal regions, comprising,
- determining an edge gradient for each of the candidate abnormal regions,
- comparing each edge gradient determined in said determining step with at least one threshold, and
- eliminating candidate abnormal regions from consideration as an abnormal region based on a result of said comparing step.
3. The method of claim 2, wherein:
- said comparing step comprises comparing each edge gradient with a predetermined number; and
- said eliminating step comprises eliminating those candidate abnormal regions having an edge gradient exceeding said predetermined number.
4. The method of claim 2, wherein:
- said comparing step comprises comparing each edge gradient with a varying threshold which varies inversely as a function of an average pixel value for the respective candidate region; and
- said eliminating step comprises eliminating those candidate abnormal regions having an edge gradient less than said varying threshold.
5. The method of claim 4, wherein said candidate abnormal region processing step comprises:
- identifying locations of microcalcifications and locations of microcalcification clusters;
- determining edge gradients for the locations of said microcalcifications and for the locations of said microcalcification clusters; and
- comparing the edge gradients determined for said microcalcification locations and for said microcalcification cluster locations with respective thresholds; and
- eliminating locations based on the comparing of microcalcification location edge gradients with respective thresholds and based on the comparing of microcalcification cluster edge gradients with respective thresholds.
6. The method according to claim 5, wherein:
- said step of determining edge gradients for the locations of said microcalcifications and for the locations of said microcalcification clusters comprises determining a degree of linearity for each of said locations identified;
- said comparing step comprises comparing the degree of linearity determined for each location with a predetermined linearity threshold; and
- said eliminating step comprises eliminating from consideration as abnormal regions locations identified in said processing step and having a linearity factor exceeding said predetermined linearity threshold.
7. The method of claims 1, 2, 3, 4, 5 or 6, wherein said obtaining step comprises obtaining a digital mammogram image.
8. The method of claims 1, 2 or 3, wherein:
- said obtaining step comprises obtaining a digital mammogram image; and
- said step of performing predetermined signal extraction and feature analysis routines comprises identifying locations of microcalcifications in the digital mammogram image.
9. A method for automated detection of an abnormal anatomic region, comprising:
- obtaining a digital image of an object including said anatomic region;
- subjecting said digital image to noise reduction filtering, comprising,
- subjecting said digital image to wavelet transformation wherein said digital image is decomposed to a set of levels each characterized by a respective wavelet coefficient;
- producing a reconstructed digital image based on wavelet coefficients that correspond to a subset of said set of levels, in which subset of levels features of the abnormal anatomic region are pronounced, in the decomposed digital image so that the reconstructed image has a clearer pattern of abnormal regions in relation to said digital image subjected to noise reduction filtering; and
- performing predetermined signal extraction and feature analysis routines on the reconstructed digital image to identify locations of candidate abnormal regions.
10. The method of claim 9, wherein:
- said obtaining step comprises obtaining a digital mammogram image; and
- said step of performing predetermined signal extraction and feature analysis routines comprises identifying locations of microcalcifications in the digital mammogram image.
4907156 | March 6, 1990 | Doi et al. |
5133020 | July 21, 1992 | Giger et al. |
5262958 | November 16, 1993 | Chui et al. |
5289374 | February 22, 1994 | Doi et al. |
- Chan et al., "Image feature analysis and computer-aided diagnosis in digital radiography", Med. Phys. vol. 14, No. 4, Jul./Aug. 1987, pp. 538-548. Chan et al., "Computer-Aided Detection of Microcalcifications in Mammograms", Investigative Radiology, Sep. 1988, vol. 23, No. 9, pp. 664-671. Chan et al., "Improvement in Radiologists' Detection of Clustered Microcalcifications on Mammograms", Investigative Radiology, vol. 25, No. 10, Oct. 1990. J. Barba et al., "Edge detection in cytology using morphological filters.", SPIE, vol. 1075, Digital Image Processing Applns. (1989), pp. 313-318. L. N. Mascio et al., "Automated analysis for microcalcifications in high resolution digital mammograms", SPIE, vol. 1898, Image Processing (1993). G. T. Bartoo et al., "Mathematical morphology techniques for image . . . ", Dept. of Bioengineering, Elec. Eng. and Pathology, University of Washington, Seattle. Nishikawa et al., "Computer-aided detection and diagnosis of masses and clustered . . . ", SPIE, vol. 1905, 1-4 Feb. 1993, pp. 422-432. Nishikawa et al., "Computer-aided detection of clustered microcalcifications": Med. Phys., vol. 20, No. 6, Nov./Dec. 1993, pg. 1661-1666. Doi et al., "Digital Radiography", Acta Radiologica 34 (1993) Fasc. 5, pg. 426-439. Matsumoto et al., "Image Feature Analysis of False-Prositive Diagnoses Produced by Automated . . . ", Investigative Radiology, vol. 27, No. 8, Aug. 1992. Katsuragawa et al., "Image feature analysis and computer-aided diagnosis . . . ", Med. Phys., vol. 15, No. 3, May/Jun. 1988, pp. 311-319. Yoshimura et al., "Computerized Scheme for the Detection of Pulmonary Nodules Investigative Radiology", Feb. 1992, vol. 27, No. 2, pp. 124-129. Jiang et al., "Method of extracting signal area and signal thickness of . . . SPIE", vol. 1778, Imaging Technologies and Applns., (1992), pp. 28-36. Giger, "Computer-aided Diagnosis", RSNA Categorical Course in Physics 1993, pp. 283-298.
Type: Grant
Filed: Aug 8, 1996
Date of Patent: Sep 30, 1997
Assignee: Arch Development Corporation (Chicago, IL)
Inventors: Robert M. Nishikawa (Chicago, IL), Takehiro Ema (Westmont, IL), Hiroyuki Yoshida (Westmont, IL), Kunio Doi (Willowbrook, IL)
Primary Examiner: Leo Boudreau
Assistant Examiner: Phuoc Tran
Law Firm: Oblon, Spivak, McClelland, Maier & Neustadt, P.C.
Application Number: 8/693,502
International Classification: G06K 900;